Google uses machine learning against DDoS attacks

Google uses machine learning against DDoS attacks

Google Cloud Armor Adaptive Protection is now available as a public preview. The service uses machine learning to differentiate between web services and DDoS attacks.

Google Cloud announced a public preview of Cloud Armor Adaptive Protection – a machine learning-based method to detect and protect enterprise applications and services from Layer 7 DDoS attacks. It’s the same technology that Google uses for Project Shield, a free service from Google parent company Alphabet that protects human rights, government, and media organizations from DDoS attacks.

Cloud Armor Adaptive Protection was launched in November as part of its DDoS Defense and Web Application Firewall (WAF) service, which provides customers with the same technology that Google uses to protect itself. With this, Google has managed to fend off incredibly large DDoS attacks in the past, including one in 2017 that reached 2.56 Tbit / s and was attributed to an attacker backed by China.

Adaptive Protection technology uses machine learning models to analyze signals across web services to identify potential attacks. It can differentiate DDoS attacks at the application layer from web applications and services and accelerates damage control by detecting abnormal traffic. “We have developed and matured this technology in recent years with internal and external development partners and testers. All Cloud Armor customers can test it for free during the preview phase, ”said Emil Kiner, product manager for Google’s Cloud Armor.

Leave a Reply

Your email address will not be published.